Merge tag 'for-5.19/drivers-2022-05-22' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Here are the driver updates queued up for 5.19. This contains:

   - NVMe pull requests via Christoph:
       - tighten the PCI presence check (Stefan Roese)
       - fix a potential NULL pointer dereference in an error path (Kyle
         Miller Smith)
       - fix interpretation of the DMRSL field (Tom Yan)
       - relax the data transfer alignment (Keith Busch)
       - verbose error logging improvements (Max Gurtovoy, Chaitanya
         Kulkarni)
       - misc cleanups (Chaitanya Kulkarni, Christoph)
       - set non-mdts limits in nvme_scan_work (Chaitanya Kulkarni)
       - add support for TP4084 - Time-to-Ready Enhancements (Christoph)

   - MD pull request via Song:
       - Improve annotation in raid5 code, by Logan Gunthorpe
       - Support MD_BROKEN flag in raid-1/5/10, by Mariusz Tkaczyk
       - Other small fixes/cleanups

   - null_blk series making the configfs side much saner (Damien)

   - Various minor drbd cleanups and fixes (Haowen, Uladzislau, Jiapeng,
     Arnd, Cai)

   - Avoid using the system workqueue (and hence flushing it) in rnbd
     (Jack)

   - Avoid using the system workqueue (and hence flushing it) in aoe
     (Tetsuo)

   - Series fixing discard_alignment issues in drivers (Christoph)

   - Small series fixing drivers poking at disk->part0 for openers
     information (Christoph)

   - Series fixing deadlocks in loop (Christoph, Tetsuo)

   - Remove loop.h and add SPDX headers (Christoph)

   - Various fixes and cleanups (Julia, Xie, Yu)"

* tag 'for-5.19/drivers-2022-05-22' of git://git.kernel.dk/linux-block: (72 commits)
  mtip32xx: fix typo in comment
  nvme: set non-mdts limits in nvme_scan_work
  nvme: add support for TP4084 - Time-to-Ready Enhancements
  nvme: split the enum used for various register constants
  nbd: Fix hung on disconnect request if socket is closed before
  nvme-fabrics: add a request timeout helper
  nvme-pci: harden drive presence detect in nvme_dev_disable()
  nvme-pci: fix a NULL pointer dereference in nvme_alloc_admin_tags
  nvme: mark internal passthru request RQF_QUIET
  nvme: remove unneeded include from constants file
  nvme: add missing status values to verbose logging
  nvme: set dma alignment to dword
  nvme: fix interpretation of DMRSL
  loop: remove most the top-of-file boilerplate comment from the UAPI header
  loop: remove most the top-of-file boilerplate comment
  loop: add a SPDX header
  loop: remove loop.h
  block: null_blk: Improve device creation with configfs
  block: null_blk: Cleanup messages
  block: null_blk: Cleanup device creation and deletion
  ...

11 files changed, 322 insertions, 228 deletions

diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index cac295cc8840..0ec5d8b9b1a4 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -1001,7 +1001,7 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	blk_limits_io_min(limits, DMZ_BLOCK_SIZE);
 	blk_limits_io_opt(limits, DMZ_BLOCK_SIZE);
 
-	limits->discard_alignment = DMZ_BLOCK_SIZE;
+	limits->discard_alignment = 0;
 	limits->discard_granularity = DMZ_BLOCK_SIZE;
 	limits->max_discard_sectors = chunk_sectors;
 	limits->max_hw_discard_sectors = chunk_sectors;
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index bfd6026d7809..d87f674ab762 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -639,14 +639,6 @@ re_read:
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
 	write_behind = le32_to_cpu(sb->write_behind);
 	sectors_reserved = le32_to_cpu(sb->sectors_reserved);
-	/* Setup nodes/clustername only if bitmap version is
-	 * cluster-compatible
-	 */
-	if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) {
-		nodes = le32_to_cpu(sb->nodes);
-		strlcpy(bitmap->mddev->bitmap_info.cluster_name,
-				sb->cluster_name, 64);
-	}
 
 	/* verify that the bitmap-specific fields are valid */
 	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -668,6 +660,16 @@ re_read:
 		goto out;
 	}
 
+	/*
+	 * Setup nodes/clustername only if bitmap version is
+	 * cluster-compatible
+	 */
+	if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) {
+		nodes = le32_to_cpu(sb->nodes);
+		strscpy(bitmap->mddev->bitmap_info.cluster_name,
+				sb->cluster_name, 64);
+	}
+
 	/* keep the array size field of the bitmap superblock up to date */
 	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);
 
@@ -695,14 +697,13 @@ re_read:
 	if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
 		set_bit(BITMAP_HOSTENDIAN, &bitmap->flags);
 	bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
-	strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
 	err = 0;
 
 out:
 	kunmap_atomic(sb);
-	/* Assigning chunksize is required for "re_read" */
-	bitmap->mddev->bitmap_info.chunksize = chunksize;
 	if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {
+		/* Assigning chunksize is required for "re_read" */
+		bitmap->mddev->bitmap_info.chunksize = chunksize;
 		err = md_setup_cluster(bitmap->mddev, nodes);
 		if (err) {
 			pr_warn("%s: Could not setup cluster service (%d)\n",
@@ -713,18 +714,18 @@ out:
 		goto re_read;
 	}
 
-
 out_no_sb:
-	if (test_bit(BITMAP_STALE, &bitmap->flags))
-		bitmap->events_cleared = bitmap->mddev->events;
-	bitmap->mddev->bitmap_info.chunksize = chunksize;
-	bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
-	bitmap->mddev->bitmap_info.max_write_behind = write_behind;
-	bitmap->mddev->bitmap_info.nodes = nodes;
-	if (bitmap->mddev->bitmap_info.space == 0 ||
-	    bitmap->mddev->bitmap_info.space > sectors_reserved)
-		bitmap->mddev->bitmap_info.space = sectors_reserved;
-	if (err) {
+	if (err == 0) {
+		if (test_bit(BITMAP_STALE, &bitmap->flags))
+			bitmap->events_cleared = bitmap->mddev->events;
+		bitmap->mddev->bitmap_info.chunksize = chunksize;
+		bitmap->mddev->bitmap_info.daemon_sleep = daemon_sleep;
+		bitmap->mddev->bitmap_info.max_write_behind = write_behind;
+		bitmap->mddev->bitmap_info.nodes = nodes;
+		if (bitmap->mddev->bitmap_info.space == 0 ||
+			bitmap->mddev->bitmap_info.space > sectors_reserved)
+			bitmap->mddev->bitmap_info.space = sectors_reserved;
+	} else {
 		md_bitmap_print_sb(bitmap);
 		if (bitmap->cluster_slot < 0)
 			md_cluster_stop(bitmap->mddev);
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 1c8a06b77c85..37cbcce3cc66 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -201,7 +201,7 @@ static struct dlm_lock_resource *lockres_init(struct mddev *mddev,
 		pr_err("md-cluster: Unable to allocate resource name for resource %s\n", name);
 		goto out_err;
 	}
-	strlcpy(res->name, name, namelen + 1);
+	strscpy(res->name, name, namelen + 1);
 	if (with_lvb) {
 		res->lksb.sb_lvbptr = kzalloc(LVB_SIZE, GFP_KERNEL);
 		if (!res->lksb.sb_lvbptr) {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 2587f872c088..707e802d0082 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2627,14 +2627,16 @@ static void sync_sbs(struct mddev *mddev, int nospares)
 
 static bool does_sb_need_changing(struct mddev *mddev)
 {
-	struct md_rdev *rdev;
+	struct md_rdev *rdev = NULL, *iter;
 	struct mdp_superblock_1 *sb;
 	int role;
 
 	/* Find a good rdev */
-	rdev_for_each(rdev, mddev)
-		if ((rdev->raid_disk >= 0) && !test_bit(Faulty, &rdev->flags))
+	rdev_for_each(iter, mddev)
+		if ((iter->raid_disk >= 0) && !test_bit(Faulty, &iter->flags)) {
+			rdev = iter;
 			break;
+		}
 
 	/* No good device found. */
 	if (!rdev)
@@ -2645,11 +2647,11 @@ static bool does_sb_need_changing(struct mddev *mddev)
 	rdev_for_each(rdev, mddev) {
 		role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
 		/* Device activated? */
-		if (role == 0xffff && rdev->raid_disk >=0 &&
+		if (role == MD_DISK_ROLE_SPARE && rdev->raid_disk >= 0 &&
 		    !test_bit(Faulty, &rdev->flags))
 			return true;
 		/* Device turned faulty? */
-		if (test_bit(Faulty, &rdev->flags) && (role < 0xfffd))
+		if (test_bit(Faulty, &rdev->flags) && (role < MD_DISK_ROLE_MAX))
 			return true;
 	}
 
@@ -2984,10 +2986,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 
 	if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
 		md_error(rdev->mddev, rdev);
-		if (test_bit(Faulty, &rdev->flags))
-			err = 0;
-		else
+
+		if (test_bit(MD_BROKEN, &rdev->mddev->flags))
 			err = -EBUSY;
+		else
+			err = 0;
 	} else if (cmd_match(buf, "remove")) {
 		if (rdev->mddev->pers) {
 			clear_bit(Blocked, &rdev->flags);
@@ -4028,7 +4031,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	oldpriv = mddev->private;
 	mddev->pers = pers;
 	mddev->private = priv;
-	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+	strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
 	mddev->level = mddev->new_level;
 	mddev->layout = mddev->new_layout;
 	mddev->chunk_sectors = mddev->new_chunk_sectors;
@@ -4353,10 +4356,9 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR,
  *     like active, but no writes have been seen for a while (100msec).
  *
  * broken
- *     RAID0/LINEAR-only: same as clean, but array is missing a member.
- *     It's useful because RAID0/LINEAR mounted-arrays aren't stopped
- *     when a member is gone, so this state will at least alert the
- *     user that something is wrong.
+*     Array is failed. It's useful because mounted-arrays aren't stopped
+*     when array is failed, so this state will at least alert the user that
+*     something is wrong.
  */
 enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
 		   write_pending, active_idle, broken, bad_word};
@@ -5763,7 +5765,7 @@ static int add_named_array(const char *val, const struct kernel_param *kp)
 		len--;
 	if (len >= DISK_NAME_LEN)
 		return -E2BIG;
-	strlcpy(buf, val, len+1);
+	strscpy(buf, val, len+1);
 	if (strncmp(buf, "md_", 3) == 0)
 		return md_alloc(0, buf);
 	if (strncmp(buf, "md", 2) == 0 &&
@@ -5896,7 +5898,7 @@ int md_run(struct mddev *mddev)
 		mddev->level = pers->level;
 		mddev->new_level = pers->level;
 	}
-	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+	strscpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
 
 	if (mddev->reshape_position != MaxSector &&
 	    pers->start_reshape == NULL) {
@@ -7443,7 +7445,7 @@ static int set_disk_faulty(struct mddev *mddev, dev_t dev)
 		err =  -ENODEV;
 	else {
 		md_error(mddev, rdev);
-		if (!test_bit(Faulty, &rdev->flags))
+		if (test_bit(MD_BROKEN, &mddev->flags))
 			err = -EBUSY;
 	}
 	rcu_read_unlock();
@@ -7984,13 +7986,16 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
 
 	if (!mddev->pers || !mddev->pers->error_handler)
 		return;
-	mddev->pers->error_handler(mddev,rdev);
-	if (mddev->degraded)
+	mddev->pers->error_handler(mddev, rdev);
+
+	if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags))
 		set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 	sysfs_notify_dirent_safe(rdev->sysfs_state);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	md_wakeup_thread(mddev->thread);
+	if (!test_bit(MD_BROKEN, &mddev->flags)) {
+		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+		md_wakeup_thread(mddev->thread);
+	}
 	if (mddev->event_work.func)
 		queue_work(md_misc_wq, &mddev->event_work);
 	md_new_event();
@@ -9670,7 +9675,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 		role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]);
 
 		if (test_bit(Candidate, &rdev2->flags)) {
-			if (role == 0xfffe) {
+			if (role == MD_DISK_ROLE_FAULTY) {
 				pr_info("md: Removing Candidate device %s because add failed\n", bdevname(rdev2->bdev,b));
 				md_kick_rdev_from_array(rdev2);
 				continue;
@@ -9683,7 +9688,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 			/*
 			 * got activated except reshape is happening.
 			 */
-			if (rdev2->raid_disk == -1 && role != 0xffff &&
+			if (rdev2->raid_disk == -1 && role != MD_DISK_ROLE_SPARE &&
 			    !(le32_to_cpu(sb->feature_map) &
 			      MD_FEATURE_RESHAPE_ACTIVE)) {
 				rdev2->saved_raid_disk = role;
@@ -9700,7 +9705,8 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 			 * as faulty. The recovery is performed by the
 			 * one who initiated the error.
 			 */
-			if ((role == 0xfffe) || (role == 0xfffd)) {
+			if (role == MD_DISK_ROLE_FAULTY ||
+			    role == MD_DISK_ROLE_JOURNAL) {
 				md_error(mddev, rdev2);
 				clear_bit(Blocked, &rdev2->flags);
 			}
@@ -9790,16 +9796,18 @@ static int read_rdev(struct mddev *mddev, struct md_rdev *rdev)
 
 void md_reload_sb(struct mddev *mddev, int nr)
 {
-	struct md_rdev *rdev;
+	struct md_rdev *rdev = NULL, *iter;
 	int err;
 
 	/* Find the rdev */
-	rdev_for_each_rcu(rdev, mddev) {
-		if (rdev->desc_nr == nr)
+	rdev_for_each_rcu(iter, mddev) {
+		if (iter->desc_nr == nr) {
+			rdev = iter;
 			break;
+		}
 	}
 
-	if (!rdev || rdev->desc_nr != nr) {
+	if (!rdev) {
 		pr_warn("%s: %d Could not find rdev with nr %d\n", __func__, __LINE__, nr);
 		return;
 	}
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 6ac283864533..cf2cbb17acbd 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -234,34 +234,42 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 				int is_new);
 struct md_cluster_info;
 
-/* change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
+/**
+ * enum mddev_flags - md device flags.
+ * @MD_ARRAY_FIRST_USE: First use of array, needs initialization.
+ * @MD_CLOSING: If set, we are closing the array, do not open it then.
+ * @MD_JOURNAL_CLEAN: A raid with journal is already clean.
+ * @MD_HAS_JOURNAL: The raid array has journal feature set.
+ * @MD_CLUSTER_RESYNC_LOCKED: cluster raid only, which means node, already took
+ *			       resync lock, need to release the lock.
+ * @MD_FAILFAST_SUPPORTED: Using MD_FAILFAST on metadata writes is supported as
+ *			    calls to md_error() will never cause the array to
+ *			    become failed.
+ * @MD_HAS_PPL:  The raid array has PPL feature set.
+ * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set.
+ * @MD_ALLOW_SB_UPDATE: md_check_recovery is allowed to update the metadata
+ *			 without taking reconfig_mutex.
+ * @MD_UPDATING_SB: md_check_recovery is updating the metadata without
+ *		     explicitly holding reconfig_mutex.
+ * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that
+ *		   array is ready yet.
+ * @MD_BROKEN: This is used to stop writes and mark array as failed.
+ *
+ * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added
+ */
 enum mddev_flags {
-	MD_ARRAY_FIRST_USE,	/* First use of array, needs initialization */
-	MD_CLOSING,		/* If set, we are closing the array, do not open
-				 * it then */
-	MD_JOURNAL_CLEAN,	/* A raid with journal is already clean */
-	MD_HAS_JOURNAL,		/* The raid array has journal feature set */
-	MD_CLUSTER_RESYNC_LOCKED, /* cluster raid only, which means node
-				   * already took resync lock, need to
-				   * release the lock */
-	MD_FAILFAST_SUPPORTED,	/* Using MD_FAILFAST on metadata writes is
-				 * supported as calls to md_error() will
-				 * never cause the array to become failed.
-				 */
-	MD_HAS_PPL,		/* The raid array has PPL feature set */
-	MD_HAS_MULTIPLE_PPLS,	/* The raid array has multiple PPLs feature set */
-	MD_ALLOW_SB_UPDATE,	/* md_check_recovery is allowed to update
-				 * the metadata without taking reconfig_mutex.
-				 */
-	MD_UPDATING_SB,		/* md_check_recovery is updating the metadata
-				 * without explicitly holding reconfig_mutex.
-				 */
-	MD_NOT_READY,		/* do_md_run() is active, so 'array_state'
-				 * must not report that array is ready yet
-				 */
-	MD_BROKEN,              /* This is used in RAID-0/LINEAR only, to stop
-				 * I/O in case an array member is gone/failed.
-				 */
+	MD_ARRAY_FIRST_USE,
+	MD_CLOSING,
+	MD_JOURNAL_CLEAN,
+	MD_HAS_JOURNAL,
+	MD_CLUSTER_RESYNC_LOCKED,
+	MD_FAILFAST_SUPPORTED,
+	MD_HAS_PPL,
+	MD_HAS_MULTIPLE_PPLS,
+	MD_ALLOW_SB_UPDATE,
+	MD_UPDATING_SB,
+	MD_NOT_READY,
+	MD_BROKEN,
 };
 
 enum mddev_sb_flags {
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 7231f5e1eaa7..e11701e394ca 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -128,21 +128,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	pr_debug("md/raid0:%s: FINAL %d zones\n",
 		 mdname(mddev), conf->nr_strip_zones);
 
-	if (conf->nr_strip_zones == 1) {
-		conf->layout = RAID0_ORIG_LAYOUT;
-	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
-		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
-		conf->layout = mddev->layout;
-	} else if (default_layout == RAID0_ORIG_LAYOUT ||
-		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
-		conf->layout = default_layout;
-	} else {
-		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
-		       mdname(mddev));
-		pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
-		err = -ENOTSUPP;
-		goto abort;
-	}
 	/*
 	 * now since we have the hard sector sizes, we can make sure
 	 * chunk size is a multiple of that sector size
@@ -273,6 +258,22 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 			 (unsigned long long)smallest->sectors);
 	}
 
+	if (conf->nr_strip_zones == 1 || conf->strip_zone[1].nb_dev == 1) {
+		conf->layout = RAID0_ORIG_LAYOUT;
+	} else if (mddev->layout == RAID0_ORIG_LAYOUT ||
+		   mddev->layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = mddev->layout;
+	} else if (default_layout == RAID0_ORIG_LAYOUT ||
+		   default_layout == RAID0_ALT_MULTIZONE_LAYOUT) {
+		conf->layout = default_layout;
+	} else {
+		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
+		       mdname(mddev));
+		pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
+		err = -EOPNOTSUPP;
+		goto abort;
+	}
+
 	pr_debug("md/raid0:%s: done.\n", mdname(mddev));
 	*private_conf = conf;
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 5aed2c8b746e..99d5af1362d7 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1641,30 +1641,39 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, "]");
 }
 
+/**
+ * raid1_error() - RAID1 error handler.
+ * @mddev: affected md device.
+ * @rdev: member device to fail.
+ *
+ * The routine acknowledges &rdev failure and determines new @mddev state.
+ * If it failed, then:
+ *	- &MD_BROKEN flag is set in &mddev->flags.
+ *	- recovery is disabled.
+ * Otherwise, it must be degraded:
+ *	- recovery is interrupted.
+ *	- &mddev->degraded is bumped.
+ *
+ * @rdev is marked as &Faulty excluding case when array is failed and
+ * &mddev->fail_last_dev is off.
+ */
 static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r1conf *conf = mddev->private;
 	unsigned long flags;
 
-	/*
-	 * If it is not operational, then we have already marked it as dead
-	 * else if it is the last working disks with "fail_last_dev == false",
-	 * ignore the error, let the next level up know.
-	 * else mark the drive as failed
-	 */
 	spin_lock_irqsave(&conf->device_lock, flags);
-	if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
-	    && (conf->raid_disks - mddev->degraded) == 1) {
-		/*
-		 * Don't fail the drive, act as though we were just a
-		 * normal single drive.
-		 * However don't try a recovery from this drive as
-		 * it is very likely to fail.
-		 */
-		conf->recovery_disabled = mddev->recovery_disabled;
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		return;
+
+	if (test_bit(In_sync, &rdev->flags) &&
+	    (conf->raid_disks - mddev->degraded) == 1) {
+		set_bit(MD_BROKEN, &mddev->flags);
+
+		if (!mddev->fail_last_dev) {
+			conf->recovery_disabled = mddev->recovery_disabled;
+			spin_unlock_irqrestore(&conf->device_lock, flags);
+			return;
+		}
 	}
 	set_bit(Blocked, &rdev->flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags))
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 834eb3ba95a6..dfa576cdf11c 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1970,32 +1970,40 @@ static int enough(struct r10conf *conf, int ignore)
 		_enough(conf, 1, ignore);
 }
 
+/**
+ * raid10_error() - RAID10 error handler.
+ * @mddev: affected md device.
+ * @rdev: member device to fail.
+ *
+ * The routine acknowledges &rdev failure and determines new @mddev state.
+ * If it failed, then:
+ *	- &MD_BROKEN flag is set in &mddev->flags.
+ * Otherwise, it must be degraded:
+ *	- recovery is interrupted.
+ *	- &mddev->degraded is bumped.
+
+ * @rdev is marked as &Faulty excluding case when array is failed and
+ * &mddev->fail_last_dev is off.
+ */
 static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r10conf *conf = mddev->private;
 	unsigned long flags;
 
-	/*
-	 * If it is not operational, then we have already marked it as dead
-	 * else if it is the last working disks with "fail_last_dev == false",
-	 * ignore the error, let the next level up know.
-	 * else mark the drive as failed
-	 */
 	spin_lock_irqsave(&conf->device_lock, flags);
-	if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
-	    && !enough(conf, rdev->raid_disk)) {
-		/*
-		 * Don't fail the drive, just return an IO error.
-		 */
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		return;
+
+	if (test_bit(In_sync, &rdev->flags) && !enough(conf, rdev->raid_disk)) {
+		set_bit(MD_BROKEN, &mddev->flags);
+
+		if (!mddev->fail_last_dev) {
+			spin_unlock_irqrestore(&conf->device_lock, flags);
+			return;
+		}
 	}
 	if (test_and_clear_bit(In_sync, &rdev->flags))
 		mddev->degraded++;
-	/*
-	 * If recovery is running, make sure it aborts.
-	 */
+
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c
index d3962d92df18..55d065a87b89 100644
--- a/drivers/md/raid5-ppl.c
+++ b/drivers/md/raid5-ppl.c
@@ -883,7 +883,9 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
 				 (unsigned long long)r_sector, dd_idx,
 				 (unsigned long long)sector);
 
-			rdev = conf->disks[dd_idx].rdev;
+			/* Array has not started so rcu dereference is safe */
+			rdev = rcu_dereference_protected(
+					conf->disks[dd_idx].rdev, 1);
 			if (!rdev || (!test_bit(In_sync, &rdev->flags) &&
 				      sector >= rdev->recovery_offset)) {
 				pr_debug("%s:%*s data member disk %d missing\n",
@@ -934,7 +936,10 @@ static int ppl_recover_entry(struct ppl_log *log, struct ppl_header_entry *e,
 		parity_sector = raid5_compute_sector(conf, r_sector_first + i,
 				0, &disk, &sh);
 		BUG_ON(sh.pd_idx != le32_to_cpu(e->parity_disk));
-		parity_rdev = conf->disks[sh.pd_idx].rdev;
+
+		/* Array has not started so rcu dereference is safe */
+		parity_rdev = rcu_dereference_protected(
+					conf->disks[sh.pd_idx].rdev, 1);
 
 		BUG_ON(parity_rdev->bdev->bd_dev != log->rdev->bdev->bd_dev);
 		pr_debug("%s:%*s write parity at sector %llu, disk %s\n",
@@ -1404,7 +1409,9 @@ int ppl_init_log(struct r5conf *conf)
 
 	for (i = 0; i < ppl_conf->count; i++) {
 		struct ppl_log *log = &ppl_conf->child_logs[i];
-		struct md_rdev *rdev = conf->disks[i].rdev;
+		/* Array has not started so rcu dereference is safe */
+		struct md_rdev *rdev =
+			rcu_dereference_protected(conf->disks[i].rdev, 1);
 
 		mutex_init(&log->io_mutex);
 		spin_lock_init(&log->io_list_lock);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 59f91e392a2a..39038fa8b1c8 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -79,18 +79,21 @@ static inline int stripe_hash_locks_hash(struct r5conf *conf, sector_t sect)
 }
 
 static inline void lock_device_hash_lock(struct r5conf *conf, int hash)
+	__acquires(&conf->device_lock)
 {
 	spin_lock_irq(conf->hash_locks + hash);
 	spin_lock(&conf->device_lock);
 }
 
 static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
+	__releases(&conf->device_lock)
 {
 	spin_unlock(&conf->device_lock);
 	spin_unlock_irq(conf->hash_locks + hash);
 }
 
 static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
+	__acquires(&conf->device_lock)
 {
 	int i;
 	spin_lock_irq(conf->hash_locks);
@@ -100,6 +103,7 @@ static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
 }
 
 static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
+	__releases(&conf->device_lock)
 {
 	int i;
 	spin_unlock(&conf->device_lock);
@@ -164,6 +168,7 @@ static bool stripe_is_lowprio(struct stripe_head *sh)
 }
 
 static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
+	__must_hold(&sh->raid_conf->device_lock)
 {
 	struct r5conf *conf = sh->raid_conf;
 	struct r5worker_group *group;
@@ -211,6 +216,7 @@ static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
 
 static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 			      struct list_head *temp_inactive_list)
+	__must_hold(&conf->device_lock)
 {
 	int i;
 	int injournal = 0;	/* number of date pages with R5_InJournal */
@@ -296,6 +302,7 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
 
 static void __release_stripe(struct r5conf *conf, struct stripe_head *sh,
 			     struct list_head *temp_inactive_list)
+	__must_hold(&conf->device_lock)
 {
 	if (atomic_dec_and_test(&sh->count))
 		do_release_stripe(conf, sh, temp_inactive_list);
@@ -350,9 +357,9 @@ static void release_inactive_stripe_list(struct r5conf *conf,
 	}
 }
 
-/* should hold conf->device_lock already */
 static int release_stripe_list(struct r5conf *conf,
 			       struct list_head *temp_inactive_list)
+	__must_hold(&conf->device_lock)
 {
 	struct stripe_head *sh, *t;
 	int count = 0;
@@ -629,6 +636,10 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector,
  * This is because some failed devices may only affect one
  * of the two sections, and some non-in_sync devices may
  * be insync in the section most affected by failed devices.
+ *
+ * Most calls to this function hold &conf->device_lock. Calls
+ * in raid5_run() do not require the lock as no other threads
+ * have been started yet.
  */
 int raid5_calc_degraded(struct r5conf *conf)
 {
@@ -686,17 +697,17 @@ int raid5_calc_degraded(struct r5conf *conf)
 	return degraded;
 }
 
-static int has_failed(struct r5conf *conf)
+static bool has_failed(struct r5conf *conf)
 {
-	int degraded;
+	int degraded = conf->mddev->degraded;
 
-	if (conf->mddev->reshape_position == MaxSector)
-		return conf->mddev->degraded > conf->max_degraded;
+	if (test_bit(MD_BROKEN, &conf->mddev->flags))
+		return true;
 
-	degraded = raid5_calc_degraded(conf);
-	if (degraded > conf->max_degraded)
-		return 1;
-	return 0;
+	if (conf->mddev->reshape_position != MaxSector)
+		degraded = raid5_calc_degraded(conf);
+
+	return degraded > conf->max_degraded;
 }
 
 struct stripe_head *
@@ -2648,6 +2659,28 @@ static void shrink_stripes(struct r5conf *conf)
 	conf->slab_cache = NULL;
 }
 
+/*
+ * This helper wraps rcu_dereference_protected() and can be used when
+ * it is known that the nr_pending of the rdev is elevated.
+ */
+static struct md_rdev *rdev_pend_deref(struct md_rdev __rcu *rdev)
+{
+	return rcu_dereference_protected(rdev,
+			atomic_read(&rcu_access_pointer(rdev)->nr_pending));
+}
+
+/*
+ * This helper wraps rcu_dereference_protected() and should be used
+ * when it is known that the mddev_lock() is held. This is safe
+ * seeing raid5_remove_disk() has the same lock held.
+ */
+static struct md_rdev *rdev_mdlock_deref(struct mddev *mddev,
+					 struct md_rdev __rcu *rdev)
+{
+	return rcu_dereference_protected(rdev,
+			lockdep_is_held(&mddev->reconfig_mutex));
+}
+
 static void raid5_end_read_request(struct bio * bi)
 {
 	struct stripe_head *sh = bi->bi_private;
@@ -2674,9 +2707,9 @@ static void raid5_end_read_request(struct bio * bi)
 		 * In that case it moved down to 'rdev'.
 		 * rdev is not removed until all requests are finished.
 		 */
-		rdev = conf->disks[i].replacement;
+		rdev = rdev_pend_deref(conf->disks[i].replacement);
 	if (!rdev)
-		rdev = conf->disks[i].rdev;
+		rdev = rdev_pend_deref(conf->disks[i].rdev);
 
 	if (use_new_offset(conf, sh))
 		s = sh->sector + rdev->new_data_offset;
@@ -2790,11 +2823,11 @@ static void raid5_end_write_request(struct bio *bi)
 
 	for (i = 0 ; i < disks; i++) {
 		if (bi == &sh->dev[i].req) {
-			rdev = conf->disks[i].rdev;
+			rdev = rdev_pend_deref(conf->disks[i].rdev);
 			break;
 		}
 		if (bi == &sh->dev[i].rreq) {
-			rdev = conf->disks[i].replacement;
+			rdev = rdev_pend_deref(conf->disks[i].replacement);
 			if (rdev)
 				replacement = 1;
 			else
@@ -2802,7 +2835,7 @@ static void raid5_end_write_request(struct bio *bi)
 				 * replaced it.  rdev is not removed
 				 * until all requests are finished.
 				 */
-				rdev = conf->disks[i].rdev;
+				rdev = rdev_pend_deref(conf->disks[i].rdev);
 			break;
 		}
 	}
@@ -2863,34 +2896,31 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
 	unsigned long flags;
 	pr_debug("raid456: error called\n");
 
+	pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n",
+		mdname(mddev), bdevname(rdev->bdev, b));
+
 	spin_lock_irqsave(&conf->device_lock, flags);
+	set_bit(Faulty, &rdev->flags);
+	clear_bit(In_sync, &rdev->flags);
+	mddev->degraded = raid5_calc_degraded(conf);
 
-	if (test_bit(In_sync, &rdev->flags) &&
-	    mddev->degraded == conf->max_degraded) {
-		/*
-		 * Don't allow to achieve failed state
-		 * Don't try to recover this device
-		 */
+	if (has_failed(conf)) {
+		set_bit(MD_BROKEN, &conf->mddev->flags);
 		conf->recovery_disabled = mddev->recovery_disabled;
-		spin_unlock_irqrestore(&conf->device_lock, flags);
-		return;
+
+		pr_crit("md/raid:%s: Cannot continue operation (%d/%d failed).\n",
+			mdname(mddev), mddev->degraded, conf->raid_disks);
+	} else {
+		pr_crit("md/raid:%s: Operation continuing on %d devices.\n",
+			mdname(mddev), conf->raid_disks - mddev->degraded);
 	}
 
-	set_bit(Faulty, &rdev->flags);
-	clear_bit(In_sync, &rdev->flags);
-	mddev->degraded = raid5_calc_degraded(conf);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 
 	set_bit(Blocked, &rdev->flags);
 	set_mask_bits(&mddev->sb_flags, 0,
 		      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
-	pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n"
-		"md/raid:%s: Operation continuing on %d devices.\n",
-		mdname(mddev),
-		bdevname(rdev->bdev, b),
-		mdname(mddev),
-		conf->raid_disks - mddev->degraded);
 	r5c_update_on_rdev_error(mddev, rdev);
 }
 
@@ -5213,23 +5243,23 @@ finish:
 			struct r5dev *dev = &sh->dev[i];
 			if (test_and_clear_bit(R5_WriteError, &dev->flags)) {
 				/* We own a safe reference to the rdev */
-				rdev = conf->disks[i].rdev;
+				rdev = rdev_pend_deref(conf->disks[i].rdev);
 				if (!rdev_set_badblocks(rdev, sh->sector,
 							RAID5_STRIPE_SECTORS(conf), 0))
 					md_error(conf->mddev, rdev);
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 			if (test_and_clear_bit(R5_MadeGood, &dev->flags)) {
-				rdev = conf->disks[i].rdev;
+				rdev = rdev_pend_deref(conf->disks[i].rdev);
 				rdev_clear_badblocks(rdev, sh->sector,
 						     RAID5_STRIPE_SECTORS(conf), 0);
 				rdev_dec_pending(rdev, conf->mddev);
 			}
 			if (test_and_clear_bit(R5_MadeGoodRepl, &dev->flags)) {
-				rdev = conf->disks[i].replacement;
+				rdev = rdev_pend_deref(conf->disks[i].replacement);
 				if (!rdev)
 					/* rdev have been moved down */
-					rdev = conf->disks[i].rdev;
+					rdev = rdev_pend_deref(conf->disks[i].rdev);
 				rdev_clear_badblocks(rdev, sh->sector,
 						     RAID5_STRIPE_SECTORS(conf), 0);
 				rdev_dec_pending(rdev, conf->mddev);
@@ -5256,6 +5286,7 @@ finish:
 }
 
 static void raid5_activate_delayed(struct r5conf *conf)
+	__must_hold(&conf->device_lock)
 {
 	if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
 		while (!list_empty(&conf->delayed_list)) {
@@ -5273,9 +5304,9 @@ static void raid5_activate_delayed(struct r5conf *conf)
 }
 
 static void activate_bit_delay(struct r5conf *conf,
-	struct list_head *temp_inactive_list)
+		struct list_head *temp_inactive_list)
+	__must_hold(&conf->device_lock)
 {
-	/* device_lock is held */
 	struct list_head head;
 	list_add(&head, &conf->bitmap_list);
 	list_del_init(&conf->bitmap_list);
@@ -5500,6 +5531,7 @@ static struct bio *chunk_aligned_read(struct mddev *mddev, struct bio *raid_bio)
  * handle_list.
  */
 static struct stripe_head *__get_priority_stripe(struct r5conf *conf, int group)
+	__must_hold(&conf->device_lock)
 {
 	struct stripe_head *sh, *tmp;
 	struct list_head *handle_list = NULL;
@@ -6288,7 +6320,7 @@ static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_n
 	 */
 	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
-		struct md_rdev *rdev = READ_ONCE(conf->disks[i].rdev);
+		struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
 
 		if (rdev == NULL || test_bit(Faulty, &rdev->flags))
 			still_degraded = 1;
@@ -6371,8 +6403,7 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio,
 static int handle_active_stripes(struct r5conf *conf, int group,
 				 struct r5worker *worker,
 				 struct list_head *temp_inactive_list)
-		__releases(&conf->device_lock)
-		__acquires(&conf->device_lock)
+		__must_hold(&conf->device_lock)
 {
 	struct stripe_head *batch[MAX_STRIPE_BATCH], *sh;
 	int i, batch_size = 0, hash;
@@ -7166,7 +7197,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	int i;
 	int group_cnt;
 	struct r5worker_group *new_group;
-	int ret;
+	int ret = -ENOMEM;
 
 	if (mddev->new_level != 5
 	    && mddev->new_level != 4
@@ -7225,6 +7256,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	spin_lock_init(&conf->device_lock);
 	seqcount_spinlock_init(&conf->gen_lock, &conf->device_lock);
 	mutex_init(&conf->cache_size_mutex);
+
 	init_waitqueue_head(&conf->wait_for_quiescent);
 	init_waitqueue_head(&conf->wait_for_stripe);
 	init_waitqueue_head(&conf->wait_for_overlap);
@@ -7302,11 +7334,13 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 
 	conf->level = mddev->new_level;
 	conf->chunk_sectors = mddev->new_chunk_sectors;
-	if (raid5_alloc_percpu(conf) != 0)
+	ret = raid5_alloc_percpu(conf);
+	if (ret)
 		goto abort;
 
 	pr_debug("raid456: run(%s) called.\n", mdname(mddev));
 
+	ret = -EIO;
 	rdev_for_each(rdev, mddev) {
 		raid_disk = rdev->raid_disk;
 		if (raid_disk >= max_disks
@@ -7317,11 +7351,11 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 		if (test_bit(Replacement, &rdev->flags)) {
 			if (disk->replacement)
 				goto abort;
-			disk->replacement = rdev;
+			RCU_INIT_POINTER(disk->replacement, rdev);
 		} else {
 			if (disk->rdev)
 				goto abort;
-			disk->rdev = rdev;
+			RCU_INIT_POINTER(disk->rdev, rdev);
 		}
 
 		if (test_bit(In_sync, &rdev->flags)) {
@@ -7370,6 +7404,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	if (grow_stripes(conf, conf->min_nr_stripes)) {
 		pr_warn("md/raid:%s: couldn't allocate %dkB for buffers\n",
 			mdname(mddev), memory);
+		ret = -ENOMEM;
 		goto abort;
 	} else
 		pr_debug("md/raid:%s: allocated %dkB\n", mdname(mddev), memory);
@@ -7383,7 +7418,8 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	conf->shrinker.count_objects = raid5_cache_count;
 	conf->shrinker.batch = 128;
 	conf->shrinker.flags = 0;
-	if (register_shrinker(&conf->shrinker)) {
+	ret = register_shrinker(&conf->shrinker);
+	if (ret) {
 		pr_warn("md/raid:%s: couldn't register shrinker.\n",
 			mdname(mddev));
 		goto abort;
@@ -7394,17 +7430,16 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	if (!conf->thread) {
 		pr_warn("md/raid:%s: couldn't allocate thread.\n",
 			mdname(mddev));
+		ret = -ENOMEM;
 		goto abort;
 	}
 
 	return conf;
 
  abort:
-	if (conf) {
+	if (conf)
 		free_conf(conf);
-		return ERR_PTR(-EIO);
-	} else
-		return ERR_PTR(-ENOMEM);
+	return ERR_PTR(ret);
 }
 
 static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded)
@@ -7621,17 +7656,18 @@ static int raid5_run(struct mddev *mddev)
 
 	for (i = 0; i < conf->raid_disks && conf->previous_raid_disks;
 	     i++) {
-		rdev = conf->disks[i].rdev;
+		rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev);
 		if (!rdev && conf->disks[i].replacement) {
 			/* The replacement is all we have yet */
-			rdev = conf->disks[i].replacement;
+			rdev = rdev_mdlock_deref(mddev,
+						 conf->disks[i].replacement);
 			conf->disks[i].replacement = NULL;
 			clear_bit(Replacement, &rdev->flags);
-			conf->disks[i].rdev = rdev;
+			rcu_assign_pointer(conf->disks[i].rdev, rdev);
 		}
 		if (!rdev)
 			continue;
-		if (conf->disks[i].replacement &&
+		if (rcu_access_pointer(conf->disks[i].replacement) &&
 		    conf->reshape_progress != MaxSector) {
 			/* replacements and reshape simply do not mix. */
 			pr_warn("md: cannot handle concurrent replacement and reshape.\n");
@@ -7749,7 +7785,6 @@ static int raid5_run(struct mddev *mddev)
 		 */
 		stripe = stripe * PAGE_SIZE;
 		stripe = roundup_pow_of_two(stripe);
-		mddev->queue->limits.discard_alignment = stripe;
 		mddev->queue->limits.discard_granularity = stripe;
 
 		blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
@@ -7828,8 +7863,8 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
 
 static void print_raid5_conf (struct r5conf *conf)
 {
+	struct md_rdev *rdev;
 	int i;
-	struct disk_info *tmp;
 
 	pr_debug("RAID conf printout:\n");
 	if (!conf) {
@@ -7840,50 +7875,54 @@ static void print_raid5_conf (struct r5conf *conf)
 	       conf->raid_disks,
 	       conf->raid_disks - conf->mddev->degraded);
 
+	rcu_read_lock();
 	for (i = 0; i < conf->raid_disks; i++) {
 		char b[BDEVNAME_SIZE];
-		tmp = conf->disks + i;
-		if (tmp->rdev)
+		rdev = rcu_dereference(conf->disks[i].rdev);
+		if (rdev)
 			pr_debug(" disk %d, o:%d, dev:%s\n",
-			       i, !test_bit(Faulty, &tmp->rdev->flags),
-			       bdevname(tmp->rdev->bdev, b));
+			       i, !test_bit(Faulty, &rdev->flags),
+			       bdevname(rdev->bdev, b));
 	}
+	rcu_read_unlock();
 }
 
 static int raid5_spare_active(struct mddev *mddev)
 {
 	int i;
 	struct r5conf *conf = mddev->private;
-	struct disk_info *tmp;
+	struct md_rdev *rdev, *replacement;
 	int count = 0;
 	unsigned long flags;
 
 	for (i = 0; i < conf->raid_disks; i++) {
-		tmp = conf->disks + i;
-		if (tmp->replacement
-		    && tmp->replacement->recovery_offset == MaxSector
-		    && !test_bit(Faulty, &tmp->replacement->flags)
-		    && !test_and_set_bit(In_sync, &tmp->replacement->flags)) {
+		rdev = rdev_mdlock_deref(mddev, conf->disks[i].rdev);
+		replacement = rdev_mdlock_deref(mddev,
+						conf->disks[i].replacement);
+		if (replacement
+		    && replacement->recovery_offset == MaxSector
+		    && !test_bit(Faulty, &replacement->flags)
+		    && !test_and_set_bit(In_sync, &replacement->flags)) {
 			/* Replacement has just become active. */
-			if (!tmp->rdev
-			    || !test_and_clear_bit(In_sync, &tmp->rdev->flags))
+			if (!rdev
+			    || !test_and_clear_bit(In_sync, &rdev->flags))
 				count++;
-			if (tmp->rdev) {
+			if (rdev) {
 				/* Replaced device not technically faulty,
 				 * but we need to be sure it gets removed
 				 * and never re-added.
 				 */
-				set_bit(Faulty, &tmp->rdev->flags);
+				set_bit(Faulty, &rdev->flags);
 				sysfs_notify_dirent_safe(
-					tmp->rdev->sysfs_state);
+					rdev->sysfs_state);
 			}
-			sysfs_notify_dirent_safe(tmp->replacement->sysfs_state);
-		} else if (tmp->rdev
-		    && tmp->rdev->recovery_offset == MaxSector
-		    && !test_bit(Faulty, &tmp->rdev->flags)
-		    && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
+			sysfs_notify_dirent_safe(replacement->sysfs_state);
+		} else if (rdev
+		    && rdev->recovery_offset == MaxSector
+		    && !test_bit(Faulty, &rdev->flags)
+		    && !test_and_set_bit(In_sync, &rdev->flags)) {
 			count++;
-			sysfs_notify_dirent_safe(tmp->rdev->sysfs_state);
+			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		}
 	}
 	spin_lock_irqsave(&conf->device_lock, flags);
@@ -7898,8 +7937,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	struct r5conf *conf = mddev->private;
 	int err = 0;
 	int number = rdev->raid_disk;
-	struct md_rdev **rdevp;
+	struct md_rdev __rcu **rdevp;
 	struct disk_info *p = conf->disks + number;
+	struct md_rdev *tmp;
 
 	print_raid5_conf(conf);
 	if (test_bit(Journal, &rdev->flags) && conf->log) {
@@ -7917,9 +7957,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 		log_exit(conf);
 		return 0;
 	}
-	if (rdev == p->rdev)
+	if (rdev == rcu_access_pointer(p->rdev))
 		rdevp = &p->rdev;
-	else if (rdev == p->replacement)
+	else if (rdev == rcu_access_pointer(p->replacement))
 		rdevp = &p->replacement;
 	else
 		return 0;
@@ -7939,18 +7979,20 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (!test_bit(Faulty, &rdev->flags) &&
 	    mddev->recovery_disabled != conf->recovery_disabled &&
 	    !has_failed(conf) &&
-	    (!p->replacement || p->replacement == rdev) &&
+	    (!rcu_access_pointer(p->replacement) ||
+	     rcu_access_pointer(p->replacement) == rdev) &&
 	    number < conf->raid_disks) {
 		err = -EBUSY;
 		goto abort;
 	}
 	*rdevp = NULL;
 	if (!test_bit(RemoveSynchronized, &rdev->flags)) {
+		lockdep_assert_held(&mddev->reconfig_mutex);
 		synchronize_rcu();
 		if (atomic_read(&rdev->nr_pending)) {
 			/* lost the race, try later */
 			err = -EBUSY;
-			*rdevp = rdev;
+			rcu_assign_pointer(*rdevp, rdev);
 		}
 	}
 	if (!err) {
@@ -7958,17 +8000,19 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
 		if (err)
 			goto abort;
 	}
-	if (p->replacement) {
+
+	tmp = rcu_access_pointer(p->replacement);
+	if (tmp) {
 		/* We must have just cleared 'rdev' */
-		p->rdev = p->replacement;
-		clear_bit(Replacement, &p->replacement->flags);
+		rcu_assign_pointer(p->rdev, tmp);
+		clear_bit(Replacement, &tmp->flags);
 		smp_mb(); /* Make sure other CPUs may see both as identical
 			   * but will never see neither - if they are careful
 			   */
-		p->replacement = NULL;
+		rcu_assign_pointer(p->replacement, NULL);
 
 		if (!err)
-			err = log_modify(conf, p->rdev, true);
+			err = log_modify(conf, tmp, true);
 	}
 
 	clear_bit(WantReplacement, &rdev->flags);
@@ -7984,6 +8028,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	int ret, err = -EEXIST;
 	int disk;
 	struct disk_info *p;
+	struct md_rdev *tmp;
 	int first = 0;
 	int last = conf->raid_disks - 1;
 
@@ -8041,7 +8086,8 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	}
 	for (disk = first; disk <= last; disk++) {
 		p = conf->disks + disk;
-		if (test_bit(WantReplacement, &p->rdev->flags) &&
+		tmp = rdev_mdlock_deref(mddev, p->rdev);
+		if (test_bit(WantReplacement, &tmp->flags) &&
 		    p->replacement == NULL) {
 			clear_bit(In_sync, &rdev->flags);
 			set_bit(Replacement, &rdev->flags);
@@ -8332,6 +8378,7 @@ static void end_reshape(struct r5conf *conf)
 static void raid5_finish_reshape(struct mddev *mddev)
 {
 	struct r5conf *conf = mddev->private;
+	struct md_rdev *rdev;
 
 	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
 
@@ -8343,10 +8390,12 @@ static void raid5_finish_reshape(struct mddev *mddev)
 			for (d = conf->raid_disks ;
 			     d < conf->raid_disks - mddev->delta_disks;
 			     d++) {
-				struct md_rdev *rdev = conf->disks[d].rdev;
+				rdev = rdev_mdlock_deref(mddev,
+							 conf->disks[d].rdev);
 				if (rdev)
 					clear_bit(In_sync, &rdev->flags);
-				rdev = conf->disks[d].replacement;
+				rdev = rdev_mdlock_deref(mddev,
+						conf->disks[d].replacement);
 				if (rdev)
 					clear_bit(In_sync, &rdev->flags);
 			}
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 9e8486a9e445..638d29863503 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -473,7 +473,8 @@ enum {
  */
 
 struct disk_info {
-	struct md_rdev	*rdev, *replacement;
+	struct md_rdev	__rcu *rdev;
+	struct md_rdev  __rcu *replacement;
 	struct page	*extra_page; /* extra page to use in prexor */
 };
 
@@ -560,6 +561,16 @@ struct r5pending_data {
 	struct bio_list bios;
 };
 
+struct raid5_percpu {
+	struct page	*spare_page; /* Used when checking P/Q in raid6 */
+	void		*scribble;  /* space for constructing buffer
+				     * lists and performing address
+				     * conversions
+				     */
+	int             scribble_obj_size;
+	local_lock_t    lock;
+};
+
 struct r5conf {
 	struct hlist_head	*stripe_hashtbl;
 	/* only protect corresponding hash list and inactive_list */
@@ -635,15 +646,7 @@ struct r5conf {
 					    */
 	int			recovery_disabled;
 	/* per cpu variables */
-	struct raid5_percpu {
-		struct page	*spare_page; /* Used when checking P/Q in raid6 */
-		void		*scribble;  /* space for constructing buffer
-					     * lists and performing address
-					     * conversions
-					     */
-		int             scribble_obj_size;
-		local_lock_t    lock;
-	} __percpu *percpu;
+	struct raid5_percpu __percpu *percpu;
 	int scribble_disks;
 	int scribble_sectors;
 	struct hlist_node node;